{
  "schemaVersion": 1,
  "generatedAt": "2026-08-10T07:59:10Z",
  "source": {
    "name": "CC-CEDICT",
    "publisher": "MDBG",
    "version": "2026-08-10",
    "releaseTimestamp": "2026-08-10T07:59:10Z",
    "originalFilename": "cedict_ts.u8",
    "originalSha256": "sha256-be95f07f7d7bfb7405d8acdc1e0cb039fb03d8ddacc0c025b42ada4975d1b641",
    "checkedInDownload": {
      "url": "https://www.mdbg.net/chinese/export/cedict/cedict_1_0_ts_utf-8_mdbg.txt.gz",
      "filename": "cedict_1_0_ts_utf-8_mdbg.txt.gz",
      "sha256": "sha256-80a3b2c91524ce4ab5d22a90b1cfdeddb7918c36cd29ebf635f958e5b67ae6cf"
    },
    "officialZipArchive": {
      "url": "https://www.mdbg.net/chinese/export/cedict/cedict_1_0_ts_utf-8_mdbg.zip",
      "filename": "cedict_1_0_ts_utf-8_mdbg.zip",
      "sha256": "sha256-b69c1e82ae4f95ae8f52d044b71d11b7e0b795b2dcb948c85c239aa03a81b667"
    },
    "license": "CC BY-SA 4.0",
    "licenseUrl": "https://creativecommons.org/licenses/by-sa/4.0/"
  },
  "rankingSource": {
    "name": "Unicode Unihan Database",
    "publisher": "The Unicode Consortium",
    "version": "17.0.0",
    "releaseDate": "2025-09-09",
    "sourceFilename": "Unihan_Readings.txt",
    "sourceSha256": "sha256-575e69c9ad85a4737a889a4f94cbd987042a90a1a6cc16dd3f4ed995c715b17c",
    "officialArchive": {
      "url": "https://www.unicode.org/Public/17.0.0/ucd/Unihan.zip",
      "filename": "Unihan.zip",
      "sha256": "sha256-f7a48b2b545acfaa77b2d607ae28747404ce02baefee16396c5d2d7a8ef34b5e"
    },
    "license": "Unicode License v3",
    "licenseUrl": "https://www.unicode.org/license.txt"
  },
  "transformation": {
    "inputFormat": "CC-CEDICT v1 UTF-8 text (`cedict_ts.u8`)",
    "outputFormat": "LangSail browser TSV v5",
    "outputLicense": "CC BY-SA 4.0 with Unicode License v3 ranking data",
    "steps": [
      "Ignore CC-CEDICT comments and metadata lines.",
      "Preserve traditional and simplified headwords and numbered pinyin.",
      "Replace slash-separated definition clauses with `｡` and semicolon gloss separators with `､`.",
      "Emit the optional HSK column as 0 because HSK labels are not CC-CEDICT source data.",
      "Rank single-character readings from Unicode Unihan kHanyuPinlu frequency counts, falling back to kMandarin preferred readings.",
      "Use definition-only penalties for proper names, abbreviations, cross-reference-only entries, and phrase-restricted readings; preserve CC-CEDICT order for ties.",
      "Derive lookup-only Jieba additions from both Hanzi headword columns.",
      "Assign deterministic fallback Jieba frequencies by word length, demote corpus-validated ambiguous additions to weak hints, and omit words already built into jieba-wasm.",
      "Exclude the four application split-rule words (面的, 都会, 都會, 他用)."
    ],
    "hskAndComponentData": "Intentionally omitted; no browser-extension-specific dictionary data is copied.",
    "gplMaterialCheck": {
      "status": "passed",
      "statement": "Generated words come only from CC-CEDICT headwords; no extension-specific GPL code or data is copied."
    }
  },
  "tokenizerRuntime": {
    "package": "jieba-wasm",
    "version": "2.4.0",
    "gitHead": "1708f27c9d785f2cdfa91d57dd70a25964a7c5a9",
    "license": "MIT",
    "sourceUrl": "https://github.com/fengkx/jieba-wasm",
    "upstream": {
      "package": "jieba-rs",
      "commit": "7f3b27375b638bc22a2efe2fd889ea60130d265c",
      "sourceUrl": "https://github.com/fengkx/jieba-rs",
      "license": "MIT"
    }
  },
  "outputs": {
    "public/language/zh/lookup-dictionary.data.tsv": {
      "sha256": "sha256-de7c44f04eb019fadec4ce8bf218191524ae8885ed825de38b9cad4b2e579a65",
      "bytes": 9824538,
      "entries": 124806
    },
    "public/language/zh/jieba-lookup-only.data.txt": {
      "sha256": "sha256-65e14369adb7d95bb9f342698202f46f47fd52f2085ff6e5db772361a91fea0b",
      "bytes": 1466609,
      "entries": 109227,
      "builtInEntriesOmitted": 88170
    },
    "combined": {
      "sha256": "sha256-6b79575131598ef2d59fcaaa99c46b7c40b8eadce3e54e7f1013b445dbb403fe"
    },
    "public/language/zh/source/cc-cedict-2026-08-10.txt.gz": {
      "sha256": "sha256-80a3b2c91524ce4ab5d22a90b1cfdeddb7918c36cd29ebf635f958e5b67ae6cf",
      "bytes": 3967284
    },
    "public/language/zh/source/unihan-readings-17.0.0.txt.gz": {
      "sha256": "sha256-f5dc0ecc11d27a7aa3dd9985217ef2b4980a92641b5a83e0a67f7ed4df22d8f0",
      "sourceSha256": "sha256-575e69c9ad85a4737a889a4f94cbd987042a90a1a6cc16dd3f4ed995c715b17c",
      "bytes": 2511128
    }
  }
}